ANIMA 2.9B version available here: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2989459/anima-29b-turbo-aio">https://civarchive.com/models/2989459/anima-29b-turbo-aio</a>Tutorial: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/36231/fixing-forge-neo-aio-detection-for-anima">Fixing recent Forge Neo to use these AIO models</a><h3 id="v5">V5</h3>Per request, V5 is a merged of ANIMA 1.1 aesthetics with Turbo V4 (at 0.9) plus my qwen heretic LoRA at 0.1. This was done in order to lower the license fee: manually adding Turbo on-site to a base fine-tuned version costs a 5 Buzz fee but a Turbo model actually costs only a 2 Buzz fee.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8a740594-2c94-4610-b42f-493745e68ef1/original=true/8a740594-2c94-4610-b42f-493745e68ef1.jpeg" />This model is thus a kind of "merge" between Turbo 1.1 and aesthetics 1.1.<h3 id="v4">V4</h3>This version is based on <a target="_blank" rel="ugc" href="https://civarchive.com/models/2619830/turbo-for-anima-less-steps?modelVersionId=3334160">Turbo V4</a>. The layers for VAE and TE are still using the old AIO format that is incompatible with current version of Forge Neo, i'll see if i can make an alternative version.<h3 id="v3.1-patch">V3.1 Patch</h3>This version is leveraging Turbo V2.9 and should be able to handle better LoRAs from my tests 😊<h3 id="v3-update">V3 update</h3>Using Turbo V3, far less qwen_heretic, no more p3-to-v1 backward move. It should be pretty close to a vanilla anima turbo, but with my own take on this aio checkpoint :D<h3 id="v2-update">V2 update</h3>Same idea as V1, sligth change in content:<pre><code>model = load_file("anima_baseV10.safetensors")
prefix_replace(model, "net.", "model.diffusion_model.")

te = load_file("qwen_3_06b_base.safetensors")
prefix_replace(te, "model.", "cond_stage_model.qwen3_06b.transformer.model.")

for k in te:
 model[k] = te[k]

merge_lora(model, "qwen-heretic-lora.safetensors", 0.4)
merge_lora(model, "Turbo-ANIMA-v1.5.safetensors", 0.9)
merge_lora(model, "anima-P3-to-V1.safetensors", -0.1)

vae = load_file("finalcut_vae.safetensors")
prefix_replace(vae, "", "first_stage_model.")
for k in vae:
 model[k] = vae[k]

save_file(model, "ANIMA-V1-Turbo-AIO_V2.safetensors")</code></pre>If reading this is too hard, the summary is:<ul><li>less change in TE (0.8 before, now 0.4)</li><li>Turbo V1.5 instead of V1</li><li>FP32 VAE instead of BF16</li></ul><h3 id="v1">V1</h3>I had some great reviews regarding <a target="_blank" rel="ugc" href="https://civarchive.com/models/2626223/narnima-turbo-all-in-one-anima-v1-checkpoint">nArnima AIO</a>, but some people would have prefered than i didn't bake in my own style to allow more flexibility... so here we go!This is ANIMA Base V1 with the same treatment as nArnima AIO without the style part of the LoRA (only TE/Turbo/Adapter LoRA).Usage:<ul><li>Resolution: Base V1 had a huge boost in quality with a final finetune at 1536x1536 resolution = Showcases picture are 960x1440 without any Hires.Fix or Upscale.</li><li>sampler/scheduler: ER_SDE + Beta (or Smoothstep for sd.cpp)</li><li>CFG: 1 since the Turbo LoRA is included (but 1.1 to 1.5 also works and allow back some negative prompting)</li><li>steps: 8-12 should be enough with the Turbo LoRA but i go for 16.</li><li>positive prompt: i like to start with masterpiece, best quality, score_9, newest, detailed</li><li>flow shift: keep the default at 3 if your tool of choice display the value</li></ul>Works with Forge Neo, should work with ComfyUI.Quantized version for sd.cpp <s>coming up on HF soon</s> is here: <a target="_blank" rel="ugc" href="https://huggingface.co/n-Arno/Anima-P3-Turbo-AIO-Q4_K/blob/main/Anima-V1-Turbo-AIO-Q4_K.gguf">https://huggingface.co/n-Arno/Anima-P3-Turbo-AIO-Q4_K/blob/main/Anima-V1-Turbo-AIO-Q4_K.gguf</a>😁PS: don't use my <a target="_blank" rel="ugc" href="https://civarchive.com/models/2600825/narnima-personal-style-for-anima">nArnima V2 LoRA</a> on top of this model as-is or the TE will get funky (not completely broken, but it may not play nice). Override this model TE with base Qwen3-0.6b if you intend to use this very specific LoRA on top (but in this case, why not use the full model?), otherwise, for any other LoRA, no problem should arise 😅<hr />Legal<span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

ANIMA-V1-Turbo-AIO

Posted on Civitai, upload found elsewhere are FORBIDDEN and done without the author permission.

Files with SHA256: dbdc10381defa5c749a5ecfde759c157e558cef85b8dc151c43e4935d6d74066